STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Beam 1.0 501B A23B vs Qwen3.5-9B

Beam 1.0 501B A23B leads Qwen3.5-9B by 21.4 points on StealthMark, 31.9 to 10.5. It leads on 8 of 9 benchmarks, including both games, and Qwen3.5-9B on 1. Beam 1.0 501B A23B scores higher on Newton's Mirror, with its largest category advantage in state at 600 ms.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

31.9/100Overall rank 42/53
10.5/100Overall rank 53/53

General Intelligence

30.9/100
7.8/100

Visual Intelligence

33.8/100
14.9/100

Reasoning efficiency

On every task, result quality and reasoning tokens are each compared with all measured models and weighed equally. Each dot is one model.

Single-step reasoning Result quality weighed against reasoning tokens on a single problem

Multi-step reasoning Result quality weighed against reasoning tokens across connected steps, as in agentic workflows

Open or local

Open modelApache 2.0
Local modelOpen model · Apache-2.0

BENCHMARK BY BENCHMARK

Where each model leads

  • Beam 1.0 501B A23B
  • Qwen3.5-9B
  • Other models
  • Median

DATASHEET

Specs and pricing

Beam 1.0 501B A23B scores higher on StealthMark and runs 6× faster in our speed test. Qwen3.5-9B is 4× cheaper per output token. Both take about 1M tokens of context.

  • Beam 1.0 501B A23B
  • Qwen3.5-9B
  • Other models
  • Median
PricePer 1M output tokens, input below
Beam 1.0 501B A23B: $1$0.25 inputQwen3.5-9B: $0.254× cheaper$0.17 input
Context windowTokens per request, max output below
Beam 1.0 501B A23B: 1MTied128K max outputQwen3.5-9B: 1.01MTied
Output speedTokens per second, our measurement
Beam 1.0 501B A23B: 9726× fastertokens/sQwen3.5-9B: 161tokens/s
SizeTotal and active parameters
Beam 1.0 501B A23B: 501B23.4B activeQwen3.5-9B: 9BAll activeEstimated
Developer
Reflection AIQwen
Released
16 Oct 20262 Mar 2026
Origin
United StatesChina
Input → output
Text → textText, image, video → text
Architecture
Sparse mixture-of-experts transformer; 52 layers (3 dense, 49 MoE), 256 experts with 8 selected per token; gated GQA and sliding-window attentionDense causal language model with vision encoder; Gated DeltaNet + gated attention; MTP-trained

Full datasheets, every price and sourceBeam 1.0 501B A23B ↗Qwen3.5-9B ↗

Anticipating threats and planning ahead. Collect coins while avoiding ghosts. Ghosts move before the player each turn, and collisions cost a life. 3 levels in sequence, up to 66 turns in total. Earlier moves and outcomes carry forward, testing learning across levels.

Beam 1.0 501B A23B 49.4/100Rank 18/47

Survived 1 of 3
Foresight: complete playing field
Level 39 ptsTurn 20 / 20

Qwen3.5-9B 12.8/100Rank 43/47

Survived 0 of 3
Foresight: complete playing field
Level 32 ptsTurn 8 / 20

Points per level

LevelBeam 1.0 501B A23BQwen3.5-9B
Level 1Second Thoughts
18 ptsOut of lives
4 ptsOut of lives
Level 2Pressure Pot
9 ptsOut of lives
4 ptsOut of lives
Level 3Hide or Flight
9 ptsSurvived
2 ptsOut of lives

Cooperative planning and learning from experience. Coordinate two robots to push numbered cores onto matching sockets. Pressure plates hold doors open; moving either robot uses one turn. 5 levels in sequence, up to 152 turns in total. Earlier moves and outcomes carry forward, testing learning across levels.

Beam 1.0 501B A23B 37.3/100Rank 29/48

Cleared 2 of 5
Latch: complete playing field
Level 55 ptsTurn 30 / 40

Qwen3.5-9B 3.8/100Rank 43/48

Cleared 1 of 5
Latch: complete playing field
Level 54.4 ptsTurn 33 / 40

Points per level

LevelBeam 1.0 501B A23BQwen3.5-9B
Level 1Hold the door
5.2 ptsCleared
5 ptsCleared
Level 2Crossfeed
9.6 ptsCleared
3.8 ptsFinished early
Level 3Relay vault
11.2 ptsFinished early
1.2 ptsFinished early
Level 4Passing bay
3.6 ptsFinished early
0.2 ptsFinished early
Level 5Second thoughts
5 ptsFinished early
4.4 ptsFinished early

Newton's Mirror

Same task instructions

Physics, perspective and recursive reflections, tested together. Explore the test ↗

The judgment

Beam 1.0 501B A23B

Central object placement is fairly close, but the defining mirrored-room structure is missing. The paint colors suggest the required contact order without establishing their different interaction histories. The faint floor oval does not demonstrate valid reflection geometry, so it earns no reflection credit. Rounded volume and glossy paint provide limited material credit despite weak metallic finishes and oversized paint bodies.

Qwen3.5-9B

Horizontal centering and a separate airborne black blob are visible. Cyan's recent contact and crimson's forward transport are insufficiently demonstrated, while sphere support remains obscured. The enlarged, lowered sphere substantially changes the composition. The wall and floor sphere images, recursive room structure and curved emitter mappings are almost entirely missing.

Score breakdown

CategoryBeam 1.0 501B A23BQwen3.5-9B
State at 600 ms20.5/253.0/25
Camera and placement11.5/154.5/15
Reflections2.0/1202.0/120
Materials and scale3.0/103.0/10
Floor-damage reward0.0/100.0/10

Benchmark task

A spinning metal sphere and paint in a mirrored room test physical reasoning, perspective and consistency across repeated reflections.

Selfie

Different task instructions

Visual construction and creative interpretation.

The judgment

Beam 1.0 501B A23B

An appealing expression and warm palette support a coherent simple cartoon. The central polishing joke is not legible: the cloth is unresolved and the nose sits away from the fan. Pointed radial plates, uncertain limb attachments and weak ground contact limit construction, while restrained surface detail limits material richness.

Qwen3.5-9B

Glowing teal spheres and a harmonious palette provide visible strengths, but the central character remains seriously unresolved. A large gap separates head and torso, limbs cannot be traced, and scattered garment shapes fail to establish the ornate costume. The foreground mound replaces the tall enclosing arch. Clean primitive edges do not repair these construction failures.

Score breakdown

CategoryBeam 1.0 501B A23BQwen3.5-9B
Task & likeness4.0/103.0/10
Anatomy & construction3.5/102.0/10
Space & placement5.5/103.0/10
Light & reflections5.5/103.5/10
Purposeful detail4.5/102.0/10
Artistry & character4.0/102.0/10
Materials & effects4.5/104.0/10
Visual integrity7.0/103.0/10

Benchmark task

Beam 1.0 501B A23B

A golden pangolin polishes its oversized amber tail while its nose smudges the same scale. The scene tests expressive anatomy, physical contact and contrasting translucent, polished and soft materials.

Qwen3.5-9B

A floating capybara in ornate robes tests character anatomy, layered fabric and the placement of surrounding luminous forms.

Mona Lisa

Different task instructions

Precise visual recall and portrait reconstruction.

The judgment

Beam 1.0 501B A23B

The candidate shows a faint warm oval against an almost entirely black field. Minimal placement and smooth tonal variation are visible, but the portrait, anatomy, crossed hands and landscape remain unreadable. The saved comparisons provide no specific evidence supporting a change to the baseline categories.

Qwen3.5-9B

A centered dark oval with sparse facial marks forms a simple graphic face, but scarcely replicates the Mona Lisa. The portrait's body, crossed hands, clothing and landscape are missing, while angular facial construction and flat tones lose its likeness, volume and subtle expression.

Score breakdown

CategoryBeam 1.0 501B A23BQwen3.5-9B
Task & likeness0.0/100.0/10
Anatomy & construction0.0/100.0/10
Space & placement0.0/100.0/10
Light & reflections0.5/100.0/10
Purposeful detail0.0/100.0/10
Artistry & character0.0/100.5/10
Materials & effects0.0/100.0/10
Visual integrity0.0/100.5/10

Benchmark task

An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.

Beach

Different task instructions

Creativity, perspective and visual beauty.

The judgment

Beam 1.0 501B A23B

A coherent, cheerful beach illustration fulfills the main subjects with clean shapes and a strong sunset focal point. Its basic geometric construction, ambiguous animal anatomy, shallow depth and schematic lighting limit its accomplishment. Decorative details provide interest without developing intricate forms or convincing physical surfaces.

Qwen3.5-9B

The beach is recognizable, and sweeping shoreline curves provide basic rhythm. Wildlife and playful activity remain poorly resolved, with ambiguous body construction and object contact. The sun glows without corresponding reflections or surface lighting. Fragmented subjects and an unintegrated rectangular panel substantially weaken composition and finish.

Score breakdown

CategoryBeam 1.0 501B A23BQwen3.5-9B
Task & likeness7.0/101.5/10
Anatomy & construction5.0/100.5/10
Space & placement6.0/101.5/10
Light & reflections5.0/101.0/10
Purposeful detail5.5/102.5/10
Artistry & character4.0/101.5/10
Materials & effects5.0/100.5/10
Visual integrity5.0/101.5/10

Benchmark task

A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.

Ground Truth

Different task instructions

Physical reasoning, light and visual reconstruction.

The judgment

Beam 1.0 501B A23B

This benchmark has not been assessed yet.

Qwen3.5-9B

This benchmark has not been assessed yet.

Benchmark task

A plank, computer mouse and blueberry in a steel room test physical stability, spatial relationships, materials and lighting.

Raccoon

Different task instructions

Scene composition and interacting subjects.

The judgment

Beam 1.0 501B A23B

A cheerful, readable illustration with recognizable animals, expressive faces and useful accessories. Simple rounded construction limits complexity, while ambiguous steering attachments and weak hull-to-water contact reduce physical coherence. Lighting and surface effects establish the setting without convincing environmental interaction.

Qwen3.5-9B

Bright colors, clean individual shapes and basic animal cues make the scene partly recognizable. Back seating, body continuity, steering and jet ski construction remain unresolved. Background gradients and wave rhythm provide some finish, but substantial anatomical, spatial and interaction weaknesses dominate.

Score breakdown

CategoryBeam 1.0 501B A23BQwen3.5-9B
Task & likeness5.0/102.5/10
Anatomy & construction3.5/101.0/10
Space & placement5.5/102.0/10
Light & reflections4.0/101.0/10
Purposeful detail6.5/101.5/10
Artistry & character3.5/101.0/10
Materials & effects5.0/101.0/10
Visual integrity6.5/102.5/10

Benchmark task

A jet-ski scene pairs a canine driver with a raccoon passenger. It tests the placement and contact of interacting subjects, along with vehicle construction.

Pelican

Different task instructions

Subject construction and spatial relationships.

The judgment

Beam 1.0 501B A23B

A cheerful, clearly readable pelican-and-bicycle illustration with clean contours and balanced composition. Simple geometric construction limits artistic complexity, while ambiguous neck and steering overlaps, merged pedal contacts and an incomplete drivetrain weaken physical coherence.

Qwen3.5-9B

The oversized bill and orderly spoked wheels make the subject partly recognizable. Clean contours and strong color contrast provide graphic clarity, but unresolved appendages, steering, drivetrain and support dominate the construction. Sparse shading and detail further limit the illustration.

Score breakdown

CategoryBeam 1.0 501B A23BQwen3.5-9B
Task & likeness5.5/104.0/10
Anatomy & construction4.5/101.5/10
Space & placement5.0/103.0/10
Light & reflections4.0/101.5/10
Purposeful detail4.0/102.5/10
Artistry & character4.0/101.5/10
Materials & effects4.0/101.5/10
Visual integrity5.5/102.5/10

Benchmark task

A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.